News for hackers. Stuff that matters.
Re:System Card: Claude Mythos Preview [pdf] by varispeed on Tuesday April 07, 2026 @05:44PM (#47681736)
Sounds like a good opportunity to pause spending on nerfed 4.6 and wait for the new model to be released and then max out over 2 weeks before it gets nerfed again.
Re:System Card: Claude Mythos Preview [pdf] by SparkyMcUnicorn on Tuesday April 07, 2026 @07:34PM (#47682697)
Re:System Card: Claude Mythos Preview [pdf] by codezero on Tuesday April 07, 2026 @08:10PM (#47682989)
the performance degradation I've seen isn't quality/completion but duration, I get good results but much less quickly than I did before 4.6. Still, it's just anecdata, but a lot of folks seem to feel the same.
Re:System Card: Claude Mythos Preview [pdf] by refulgentis on Tuesday April 07, 2026 @09:10PM (#47683488)
Been reading posts like these for 3 years now. There’s multiple sites with #s. I’m willing to buy “I’m paying rent on someone’s agent harness and god knows what’s in the system prompt rn”, but in the face of numbers, gotta discount the anecdotal.
Re:System Card: Claude Mythos Preview [pdf] by coldtea on Wednesday April 08, 2026 @05:58AM (#47687913)
Yeah, why trust your actual experience over numbers? Nothing surer than synthetic benchmarks
Re:System Card: Claude Mythos Preview [pdf] by refulgentis on Wednesday April 08, 2026 @07:09AM (#47688565)
Strawman, and, synthetic benchmark? :)
Re:System Card: Claude Mythos Preview [pdf] by codezero on Wednesday April 08, 2026 @01:42PM (#47693648)
You're probably right. It's probably more likely that for some period of time I forgot that I switched to the large context Opus vs Sonnet and it was not needed for the level of complexity of my work.
Re:System Card: Claude Mythos Preview [pdf] by andai on Wednesday April 08, 2026 @06:19AM (#47688080)
This just looks like random noise to me? Is it also random on short timespans, like running it 10x in a row?
Re:System Card: Claude Mythos Preview [pdf] by SparkyMcUnicorn on Wednesday April 08, 2026 @08:03PM (#47697736)
Explained in the methodology at the bottom of this page: https://marginlab.ai/trackers/claude-code/
Re:System Card: Claude Mythos Preview [pdf] by dns_snek on Wednesday April 08, 2026 @08:32AM (#47689289)
I don't believe that trackers like this are trustworthy. There's an enormous financial motive to cheat and these companies have a track record of unethical conduct.

If I was VP of Unethical Business Strategy at OpenAI or Anthropic, the first thing I'd do is put in place an automated system which flags accounts, prompts, IPs, and usage patterns associated with these benchmarks and direct their usage to a dedicated compute pool which wouldn't be affected by these changes.